Detecting backdoored language models at scale

Today, we are releasing new research on detecting backdoors in open-weight language models. Our research highlights several key properties of language model backdoors, laying the groundwork for a practical scanner designed to detect backdoored models at scale and improve overall trust in AI...

CVE-2025-64502 Parse Server allows public `explain` queries which may expose sensitive database performance information and schema details

Parse Server is an open source backend that can be deployed to any infrastructure that can run Node.js. The MongoDB explain method provides detailed information about query execution plans, including index usage, collection scanning behavior, and performance metrics. Prior to version 8.5.0-alpha....

The 2021 OWASP Top 10 Have Evolved: Here's What You Should Know

Late last week, the Open Web Application Security Project OWASP released its top 10 list of critical web application security risks. The last OWASP Top 10 came out in 2017, and in the intervening 4 years, we've seen a fundamental shift in application security that includes greater emphasis on...

Deployment Isn’t the Final Step – Monitoring Machine Learning Models in Production

Unless you’ve been living in a cave for the last decade, you’ve probably heard of the concept of a machine learning system at least once in your life. Whether it’s auto-translation, auto-completion, face or voice recognition, recommendation systems or autonomous driving, AI-based systems can be...